Vehicle localisation

Abstract

The present disclosure relates to a method for determining a vehicle pose, predicting a pose (x k , y k , θ k ) of vehicle on a map based on sensor data acquired by a vehicle localization system, transforming a set of map road references of a segment of a digital map from a global coordinate system to an image-frame coordinate system of a vehicle-mounted camera based on map data and predicted pose of the vehicle. The transformed set of map road references form a set of polylines in image-frame coordinate system. Identifying a set of corresponding image road reference features in an image acquired by vehicle mounted camera, where each identified road references feature defines a set of measurement coordinates (x i , y i ) in image-frame. Projecting each of identified set of image road reference features onto formed set of polylines in order to obtain a set of projection points.

What is claimed is: 
     
       1. A method for determining a vehicle pose, the method comprising:
 predicting a pose of the vehicle on a map based on sensor data acquired by a vehicle localization system; 
 transforming a set of map road references of a segment of a digital map from a global coordinate system to an image-frame coordinate system of a vehicle-mounted camera based on map data and the predicted pose of the vehicle, wherein the transformed set of map road references form a set of polylines in the image-frame coordinate system; 
 identifying a set of corresponding image road reference features in an image acquired by the vehicle-mounted camera, each identified road references feature defining a set of measurement coordinates in the image-frame; 
 projecting each of the identified set of image road reference features onto the formed set of polylines in order to obtain a set of projection points, wherein each projection point defines a set of projection coordinates; 
 determining an error parameter based on a difference between the measurement coordinates and the corresponding projection coordinates; 
 updating the predicted pose based on the determined error parameter; and 
 controlling the vehicle based on the updated pose. 
 
     
     
       2. The method according to  claim 1 , wherein the step of transforming the set of map road reference comprises:
 converting the set of map road references of the segment of the digital map from the global coordinate system into an ego-frame coordinate system of the vehicle based on map data and the predicted pose; and 
 transforming the converted set of map road references of the segment from the ego-frame coordinate system to the image-frame coordinate system based on a set of calibration parameters of the vehicle-mounted camera. 
 
     
     
       3. The method according to  claim 2 , wherein the calibration parameters include a set of camera extrinsic parameters and a set of camera intrinsic parameters. 
     
     
       4. The method according to  claim 1 , wherein the step of predicting a pose of the vehicle comprises predicting a pose of the vehicle on a map based on sensor data acquired by the vehicle localization system and a predefined vehicle motion model. 
     
     
       5. The method according to  claim 1 , wherein the step of projecting the identified set of image road reference features comprises:
 for each identified image road reference feature, defining a closest index of each polyline relative to the image road reference feature as the projection point for that image road reference feature. 
 
     
     
       6. The method according to  claim 5 , further comprising:
 validating the identified set of image road reference features by: 
 for each image road reference feature, discarding the image road reference features and the associated projection points if one of the associated projection points is a non-orthogonal projection point; 
 wherein the determination of the error parameter is only based on a difference between the measurement coordinates of validated road reference features and the corresponding projection coordinates. 
 
     
     
       7. The method according to  claim 1 , wherein the step of predicting the pose of the vehicle comprises:
 predicting the pose of the vehicle using a Bayesian filter. 
 
     
     
       8. The method according to  claim 1 , wherein the step of predicting the pose of the vehicle comprises perturbing an estimated current vehicle pose and propagating the perturbed vehicle pose; and
 wherein the transformation of the set of map road references are based on the perturbed vehicle poses. 
 
     
     
       9. The method according to  claim 8 , wherein the perturbing an estimated current vehicle pose and propagating the perturbed vehicle poses is based on prediction and measurement models of a Cubature Kalman Filter, and wherein the perturbed vehicle poses correspond to cubature points. 
     
     
       10. The method according to  claim 1 , further comprising:
 selecting the segment of the digital map based on the predicted pose of the vehicle and a set of properties of the vehicle-mounted camera. 
 
     
     
       11. A non-transitory computer-readable storage medium storing one or more instructions configured to be executed by one or more processors of a vehicle localization module, the one or more instructions for performing the method according to  claim 1 . 
     
     
       12. A device for determining a vehicle pose, the device comprising control circuitry configured to:
 predict a pose of the vehicle on a map based on sensor data acquired by a vehicle localization system; 
 transform a set of map road references of a segment of a digital map from a global coordinate system to an image-frame coordinate system of a vehicle-mounted camera based on map data and the predicted pose of the vehicle, wherein the transformed set of map road references form a set of polylines in the image-frame coordinate system; 
 identify a set of corresponding image road reference features in an image acquired by the vehicle-mounted camera, each identified image road references feature defining a set of measurement coordinates in the image-frame; 
 project each of the set of identified road reference features onto the formed set of polylines in order to obtain a set of projection points, wherein each projection point defines a set of projection coordinates; 
 determine an error parameter based on a difference between the measurement coordinates and the corresponding projection coordinates; 
 update the predicted pose based on the determined error parameter; and 
 control the vehicle based on the updated pose. 
 
     
     
       13. A vehicle comprising:
 a localization system for monitoring a position of the vehicle; 
 a vehicle-mounted camera for capturing images of a surrounding environment of the vehicle; 
 a device for determining a vehicle pose, the device comprising control circuitry configured to: 
 predict a pose of the vehicle on a map based on sensor data acquired by a vehicle localization system; 
 transform a set of map road references of a segment of a digital map from a global coordinate system to an image-frame coordinate system of a vehicle-mounted camera based on map data and the predicted pose of the vehicle, wherein the transformed set of map road references form a set of polylines in the image-frame coordinate system; 
 identify a set of corresponding image road reference features in an image acquired by the vehicle-mounted camera, each identified image road references feature defining a set of measurement coordinates in the image-frame; 
 project each of the set of identified road reference features onto the formed set of polylines in order to obtain a set of projection points, wherein each projection point defines a set of projection coordinates; 
 determine an error parameter based on a difference between the measurement coordinates and the corresponding projection coordinates 
 update the predicted pose based on the determined error parameter; and 
 control the vehicle based on the updated pose.